Skip to main content
Glama
304,923 tools. Last updated 2026-07-21 23:53

"Resources for Analyzing Stock Patterns" matching MCP tools:

Matching MCP Servers

  • F
    license
    -
    quality
    C
    maintenance
    A production-grade MCP server that provides tools to fetch historical stock data, company information, and technical indicators (SMA, EMA, RSI, MACD, Bollinger Bands) via yfinance, and includes a Flask web dashboard for visual analysis.
    Last updated

Matching MCP Connectors

  • Korean stock market data - prices, dividends, short selling, financial disclosures

  • Korea stock (KOSPI/KOSDAQ) bottom/top signals: verdict + score, scans. Pay-per-call x402.

  • Validates @appolabs/appo SDK setup by analyzing package.json and optionally checking import patterns to confirm correct configuration.
    MIT
  • Monitor recent autovacuum and autoanalyze activity patterns to analyze execution history, frequency, timing intervals, and identify tables with irregular vacuum patterns in PostgreSQL databases.
    MIT
  • Detect pump-and-dump operator activity in NSE stocks by analyzing volume spikes, price surges, and circuit patterns. Returns pump probability, red flags, and recommendations.
    MIT
  • Calculate current stock holdings by analyzing trade history to show net shares for each symbol with positive balances.
    MIT
  • Extract and categorize all links from a webpage to build sitemaps, analyze site structure, find broken links, or discover resources. Groups links by type for efficient web analysis.
    MIT
  • Discover related tables by analyzing shared key fields to identify parent/child relationships, common join patterns, and related configuration tables in PeopleSoft databases.
    MIT
  • Retrieve current stock snapshot for a connected store, including out-of-stock and low-stock items sorted by urgency.
    MIT
  • List tiles a city can purchase with gold, showing cost, terrain, and resources. Prioritizes tiles with luxury or strategic resources.
    MIT
  • Suggests relevant tools and workflows by analyzing time of day, day of week, and personal usage patterns.
    MIT